Thank you for sending your enquiry! One of our team members will contact you shortly.
Thank you for sending your booking! One of our team members will contact you shortly.
Duration 7 hours
Course Outline
Overview of Huawei’s AI Ecosystem
- Ascend AI hardware: 310, 910, and 910B chips
- MindSpore, CANN, and auxiliary tools
- AI development process: from training to deployment
Grasping the CANN Toolkit
- Definition of CANN and its significance
- Summary of key components (ATC, AscendCL, operator libraries)
- CANN’s role in AI inference pipelines
Commencing with MindSpore and CANN
- Environment configuration (MindSpore + CANN + Python)
- Training a basic model within MindSpore
- Model export and conversion via ATC
Executing Inference on Ascend Devices
- Utilizing the OM model through AscendCL or Python APIs
- Basic input/output preprocessing techniques
- Verification of model outputs
Integrating with Other Frameworks
- Support overview for TensorFlow, PyTorch, and ONNX
- Compatible operators and known limitations
- Demonstration of simple model conversion (e.g., from ONNX to OM)
Discovering the CANN and MindSpore Developer Ecosystem
- Essential resources: documentation, GitHub repositories, and sample code
- MindSpore Hub and model zoo introduction
- Community forums, events, and support channels
Conclusion and Subsequent Steps
Requirements
- Fundamental understanding of machine learning and deep learning principles
- Proficiency in programming with Python
- No previous experience with CANN or Ascend hardware is necessary
Target Audience
- Machine learning developers investigating deployment workflows
- Students or researchers unfamiliar with Huawei’s AI ecosystem
- AI framework contributors and enthusiasts interested in model acceleration
